Extending the weightless WiSARD classifier for regression

•Weightless Artificial Neural Networks (WANNs) are known to be more cheaper and faster than traditional neural networks.•WiSARD is the most adopted WANN model, having already been used in many different tasks and domains.•ClusWiSARD is an extension that improves accuracy in tasks where patterns of the same class are very heterogeneous.•The n-Tuple Regression Network (nTRN) was the only WANN model capable of performing regression.•This work proposes new models: Regression WiSARD and ClusRegression WiSARD, which are based in nTRN, WiSARD and ClusWiSARD.•In this work the novel proposed models are analyzed, including in the exploration of three different ensemble architectures.